Autonomously implements the next DEVSPEC.md task: syncs the spec, selects a pending task, changes code and tests, runs up to three repair cycles, updates task status, and optionally creates a scoped commit. Use for "auto code", "自动开发", "自动写代码", "auto dev", "一键开发", "autopilot", or other requests to continue spec-driven…
Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QATESTPLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks.…
Guide for creating effective agent skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations. Use when user says "create skill", "new skill", "build a skill", "update skill", or…
A mock technical-interview agent for the Modular RAG MCP Server project. RAG means retrieval-augmented generation: an AI system retrieves relevant information before generating an answer.
Clean and package the project for distribution. Removes Python caches, build artifacts, data caches, logs, IDE files, coverage reports, and sanitizes API keys in config while leaving the external Conda environment untouched. Produces a minimal, ready-to-share codebase. Use when user says 'package', 'clean project'…
An interactive study guide for a Modular RAG MCP Server project. RAG means retrieving relevant information before generating an answer, and MCP is a way for tools to connect to an agent.
Interactive project setup wizard. From a clean codebase, guides user through provider selection (OpenAI/Azure/DeepSeek/Ollama/Qwen/Gemini/etc.), API key configuration, dependency installation, config generation, and launches the dashboard. If user selects an unimplemented provider, auto-scaffolds the provider code…